This repository was archived by the owner on Oct 23, 2025. It is now read-only.
This repository was archived by the owner on Oct 23, 2025. It is now read-only.
Tests #7
Description
- Deterministic tests (make sure SDK is being used correctly from client). Includes LLM invokation with simple prompts to verify responses + function calls make sense
- Agentic-test => an evaluator agent observes another agent's logs (thinking) and result (output) and provides feedback on performance and decides if to fail test, raise warning, or pass (possibly based on a passed rubric)
(TO BE RESEARCHED: how other pple are testing their agents9